Hierarchical Face Aging Through Disentangled Latent Characteristics | |
Li PP(李佩佩) | |
2021 | |
会议日期 | 2021-8 |
会议地点 | online |
英文摘要 | Current age datasets lie in a long-tailed distribution, which brings difficulties to describe the aging mechanism for the imbalance ages. To alleviate it, we design a novel facial age prior to guide the aging mechanism modeling. To explore the age effects on facial images, we propose a Disentangled Adversarial Autoencoder (DAAE) to disentangle the facial images into three independent factors: age, identity and extraneous information. To avoid the “wash away” of age and identity information in face aging process, we propose a hierarchical conditional generator by passing the disentangled identity and age embeddings to the high-level and low-level layers with class-conditional BatchNorm. Finally, a disentangled adversarial learning mechanism is introduced to boost the image quality for face aging. In this way, when manipulating the age distribution, DAAE can achieve face aging with arbitrary ages. Further, given an input face image, the mean value of the learned age posterior distribution can be treated as an age estimator. These indicate that DAAE can efficiently and accurately estimate the age distribution in a disentangling manner. DAAE is the first attempt to achieve facial age analysis tasks, including face aging with arbitrary ages, exemplar-based face aging and age estimation, in a universal framework. The qualitative and quantitative experiments demonstrate the superiority of DAAE on five popular datasets, including CACD2000, Morph, UTKFace, FG-NET and AgeDB. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44786] |
专题 | 自动化研究所_智能感知与计算研究中心 |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li PP. Hierarchical Face Aging Through Disentangled Latent Characteristics[C]. 见:. online. 2021-8. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论